[mlpack-git] [mlpack/mlpack] Neural evolution algorithms implementation (CNE, NEAT, HyperNEAT) (#686)

Marcus Edel notifications at github.com
Wed Aug 17 14:13:07 EDT 2016


> +  /**
> +   * Parametric constructor.
> +   *
> +   * @param id Neuron's ID.
> +   * @param type Neuron's type: INPUT, BIAS, HIDDEN, OUTPUT.
> +   * @param actFuncType The type of activation function.
> +   * @param depth The depth of the neuron.
> +   * @param coordinate The coordinate of the neuron.
> +   * @param input Neuron's input value.
> +   * @param activation Neuron's activation value.
> +   */
> +  NeuronGene(int id,
> +  	         NeuronType type,
> +  	         ActivationFuncType actFuncType,
> +             double depth,
> +             std::vector<double> coordinate,

I think it would be a good idea to provide another constructor, that uses a default value for ``coordinate``. So that I can use:

```
NeuronGene inputGene1(0, INPUT, LINEAR, 0, 0, 0);
```

instead of:

```
NeuronGene inputGene1(0, INPUT, LINEAR, 0, std::vector<double>(), 0, 0);
```

-- 
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/mlpack/mlpack/pull/686/files/62d58851488dea35cac71c62352619eacba4ce3b#r75176269
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mailman.cc.gatech.edu/pipermail/mlpack-git/attachments/20160817/e07988a9/attachment.html>


More information about the mlpack-git mailing list